Automated social agent interaction quality monitoring and improvement

Number: 11727916
Published: 2023-08-15
Filed: 2021-05-20
Assignee: Disney Enterprises, Inc.
Inventors: Kennedy; James R. et al.
CPC: G01S13/865; G06V40/20; G10L15/01; G06V40/174; G06F3/167; G10L15/1807; G10L15/22; G10L15/26; G01S13/867; G10L13/027; G06V40/193; G06F40/00
Verdict: Low Notable software
Source: Google Patents · FreePatentsOnline

The keeper's note

Interaction-quality monitoring/improvement for interactive social agents (granted).

Abstract

A system for monitoring and improving social agent interaction quality includes a computing platform having processing hardware and a system memory storing a software code. The processing hardware is configured to execute the software code to receive, from a social agent, interaction data describing an interaction of the social agent with a user, and to perform an assessment of the interaction, using the interaction data, as one of successful or including a flaw. When the assessment indicates that the interaction includes the flaw, the processing hardware is further configured to execute the software code to identify an interaction strategy for correcting the flaw, and to deliver, to the social agent, one or both of the assessment and the interaction strategy to correct the flaw in the interaction.

Background

BACKGROUND (1) Advances in artificial intelligence have led to the development of a variety of devices providing dialogue-based interfaces that simulate social agents. However, one typical shortcoming of conventional social agents is their inability to engage in natural, fluid conversations, or to engage with more than one person at a time. Moreover, although existing social agents offer some degree of user personalization, for example tailoring responses to an individual user's characteristics or preferences, that personalization remains limited by their fundamentally transactional design. That is to say, their transactional functionality makes it unnecessary for conventional social agents to remember more than a limited set of predefined keywords, such as user names and basic user preferences. Moreover, conventional social agents are typically unable to recover from conversational breakdowns, and instead tend to terminate the interaction with a predetermined phrase such as: “I'm having trouble understanding right now.” Thus, there is a need in the art for an automated solution for monitoring and improving the interaction quality of a social agent so as to enable interactions with multiple users concurrently in a natural and engaging manner.

Claims

1. A system for monitoring and improving a social agent interaction quality, the system comprising: a computing platform including processing hardware and a system memory; a software code stored in the system memory; the processing hardware configured to execute the software code to: receive, from a social agent, an interaction data describing an interaction of the social agent with a user; perform an assessment of the interaction, using the interaction data, to determine whether the interaction includes a flaw based on a comparison of a predicted interactive expression by the user to an actual expression used by the user and included in the interaction data; when the assessment indicates that the interaction includes the flaw, identify an interaction strategy for correcting the flaw; and deliver, to the social agent, at least one of the assessment or the interaction strategy to correct the flaw in the interaction. || 11. A method for use by a system for monitoring and improving a social agent interaction quality, the system including a computing platform having processing hardware and a system memory storing a software code, the method comprising: receiving from a social agent, by the software code executed by the processing hardware, an interaction data describing an interaction of the social agent with a user; performing an assessment of the interaction, by the software code executed by the processing hardware and using the interaction data, to determine whether the interaction includes a flaw based on a comparison of a predicted interactive expression by the user to an actual expression used by the user and included in the interaction data; when the assessment indicates that the interaction includes the flaw, identifying, by the software code executed by the processing hardware, an interaction strategy for correcting the flaw; and delivering to the social agent, by the software code executed by the processing hardware, at least one of the assessment or the interaction strategy to correct the flaw in the interaction.